Demand prediction assistance apparatus, demand prediction assistance method, and demand prediction assistance program

Abstract

To realize a demand prediction assistance apparatus that enables efficient prediction reassessment for each product.SOLUTION: A demand prediction assistance apparatus includes: first display means for displaying information indicating a product which requires a prediction reassessment, on the basis of a plurality of indices calculated using a predicted value which is a result of a demand prediction of each of a plurality of products or a planned value which is a result of a shipment plan of each of the plurality of products, the plurality of indices including (i) a first index which indicates a degree of divergence between an actual outcome value of past sales and the predicted value for each product and (ii) a second index which indicates a result of comparison between the predicted value or the planned value for a certain future period and an estimated value of sales for the certain future period for each product; reception means for receiving a user's selection with respect to the product displayed by the first display means; and second display means for displaying an analysis result regarding demand for a product corresponding to the selection received by the reception means.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to a demand forecasting support device, a demand forecasting support method, and a demand forecasting support program. [Background technology]

[0002] Technologies for performing demand forecasting are known. One example of a technology for performing demand forecasting is the technology described in Patent Document 1. Patent Document 1 describes an order quantity proposal support system having a demand forecasting unit that calculates a demand forecast value that predicts demand using a demand forecasting model that predicts demand for a target item, and an error prediction unit that evaluates an error using an error prediction model that predicts a future error in the demand forecast value. In the order quantity proposal support system described in Patent Document 1, the demand forecasting unit extracts feature quantities from actual data related to the demand for the target item and predicts demand based on the feature quantities. The error prediction unit predicts an error based on the actual data, the demand forecast value, and the feature quantities. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2020-102133 Summary of the Invention [Problem to be solved by the invention]

[0004] Planners and other users who use the results of demand forecasts understand the accuracy of the demand forecasts and review the forecasts for each product. In this case, the more types of products are targeted for demand forecasts, the greater the cost required to review the forecasts for each product. Patent Document 1 also has a similar problem.

[0005] The present disclosure has been made in consideration of the above-mentioned problems, and an exemplary purpose thereof is to provide a technology that allows a user to efficiently review forecasts for each product. [Means for solving the problem]

[0006] A demand forecasting support device according to an exemplary aspect of the present disclosure includes a first display means for displaying information representing products whose forecasts require revision based on a plurality of indicators calculated using forecast values ​​that are the result of demand forecasts for each of a plurality of products or planned values ​​that are the result of shipping plans, the plurality of indicators including (i) a first indicator that represents the degree of deviation between the actual past sales value of each product and the forecast value, and (ii) a second indicator that represents the result of a comparison between the forecast value or the planned value for each product for a certain future period and the expected sales value for that period; a reception means for receiving a user's selection for the products displayed by the first display means; and a second display means for displaying an analysis result regarding demand for the product corresponding to the selection received by the reception means.

[0007] A demand forecasting support method according to an exemplary aspect of the present disclosure includes: a first display process in which at least one processor displays information indicating products for which forecasts need to be revised based on a plurality of indices calculated using forecast values ​​that are the result of demand forecasts for each of a plurality of products or planned values ​​that are the result of shipping plans, the plurality of indices including: (i) a first indice that indicates the degree of deviation between actual past sales values ​​of each product and the forecast values; and (ii) a second indice that indicates a comparison result between the forecast values ​​or the planned values ​​for each product for a certain future period and expected sales values ​​for that period; The method includes a reception process in which the at least one processor receives a user's selection for a product displayed in the first display process, and a second display process in which the at least one processor displays an analysis result regarding demand for the product corresponding to the selection received in the reception process.

[0008] A demand forecasting support program according to an exemplary aspect of the present disclosure is a program for causing a computer to function as a demand forecasting support device, and causes the computer to function as a first display means for displaying information representing products whose forecasts require revision based on a plurality of indicators calculated using forecast values ​​that are the result of demand forecasts for each of a plurality of products or planned values ​​that are the result of shipping plans, the plurality of indicators including (i) a first indicator that represents the degree of deviation between the actual past sales value of each product and the forecast value, and (ii) a second indicator that represents the result of a comparison between the forecast value or the planned value for each product for a certain future period and the expected sales value for that period; a reception means for receiving a user's selection for the products displayed by the first display means; and a second display means for displaying an analysis result regarding demand for the product corresponding to the selection received by the reception means. [Effects of the Invention]

[0009] According to an exemplary aspect of the present disclosure, an exemplary effect is achieved in that a technology can be provided that allows a user to efficiently review forecasts for each product. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a block diagram illustrating a configuration of a demand forecasting support device according to the present disclosure. [Figure 2] 1 is a flow diagram showing the flow of a demand forecasting support method according to the present disclosure. [Figure 3] FIG. 1 is a diagram showing an example of an overview of the forecast / plan accuracy management operation according to the present disclosure. [Figure 4] FIG. 1 is a block diagram illustrating a configuration of a quality control system according to the present disclosure. [Figure 5] 1 is a block diagram illustrating a configuration of an information processing device according to the present disclosure. [Figure 6] FIG. 1 illustrates an example of a weighted MAPE calculation according to the present disclosure. [Figure 7] FIG. 10 is a diagram illustrating an example of calculating an f-Bias rate according to the present disclosure. [Figure 8] FIG. 10 is a diagram illustrating an example of calculating FVA according to the present disclosure. [Figure 9] 10A to 10C are diagrams illustrating an overview of screen transitions displayed by a display control unit according to the present disclosure. [Figure 10] FIG. 10 is a diagram illustrating an example of an overall summary screen according to the present disclosure. [Figure 11] FIG. 10 is a diagram illustrating another example of a graph displayed on the overall summary screen according to the present disclosure. [Figure 12] FIG. 10 is a diagram illustrating another example of a graph displayed on the overall summary screen according to the present disclosure. [Figure 13] FIG. 10 is a diagram illustrating an example of a screen for information by brand and category in charge according to the present disclosure. [Figure 14] FIG. 10 is a diagram showing another example of a graph displayed on the information screen by brand and category in charge according to the present disclosure. [Figure 15] FIG. 10 is a diagram showing another example of a graph displayed on the information screen by brand and category in charge according to the present disclosure. [Figure 16] FIG. 10 is a diagram illustrating an example of a MAPE impact list screen according to the present disclosure. [Figure 17] FIG. 10 is a diagram illustrating another example of a MAPE impact list screen according to the present disclosure. [Figure 18] FIG. 10 is a diagram illustrating an example of a product metrics analysis screen according to the present disclosure. [Figure 19] FIG. 10 is a diagram illustrating another example of a graph displayed on the product metrics analysis screen according to the present disclosure. [Figure 20] FIG. 10 is a diagram illustrating an example of an alert screen according to the present disclosure. [Figure 21] FIG. 10 is a diagram visually illustrating features of an alert according to the present disclosure. [Figure 22] FIG. 10 is a diagram illustrating an example of a forecast value review screen according to the present disclosure. [Figure 23] FIG. 2 is a block diagram illustrating an example of the configuration of a user terminal according to the present disclosure. [Figure 24] FIG. 2 is a sequence diagram showing an example of the flow of a demand forecasting support method according to the present disclosure. [Figure 25] FIG. 2 is a sequence diagram showing an example of the flow of a demand forecasting support method according to the present disclosure. [Figure 26] 1 is a block diagram illustrating a configuration of a computer that functions as a demand forecasting support device and an information processing device according to the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0011] The following are examples of embodiments of the present invention. However, the present invention is not limited to the exemplary embodiments shown below, and various modifications are possible within the scope of the claims. For example, embodiments obtained by appropriately combining the technologies (part or all of the products or methods) employed in the exemplary embodiments shown below may also be included in the scope of the present invention. Furthermore, embodiments obtained by appropriately omitting some of the technologies employed in the exemplary embodiments shown below may also be included in the scope of the present invention. Furthermore, the effects mentioned in the exemplary embodiments shown below are examples of effects expected in the exemplary embodiments, and do not define the scope of the present invention. In other words, embodiments that do not exhibit the effects mentioned in the exemplary embodiments shown below may also be included in the scope of the present invention.

[0012] First Exemplary Embodiment A first exemplary embodiment, which is an example of an embodiment of the present invention, will be described in detail with reference to the drawings. This exemplary embodiment is a basic form for each of the exemplary embodiments described below. Note that the scope of application of each technique employed in this exemplary embodiment is not limited to this exemplary embodiment. That is, each technique employed in this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical obstacles arise. Furthermore, each technique shown in the drawings referenced to explain this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical obstacles arise.

[0013] (Configuration of the demand forecasting support device) The configuration of the demand forecasting support device 1 will be described with reference to Fig. 1. Fig. 1 is a block diagram showing the configuration of the demand forecasting support device 1. As shown in Fig. 1, the demand forecasting support device 1 includes a first display unit 11, a reception unit 12, and a second display unit 13.

[0014] The first display unit 11 displays information indicating products whose forecasts require revision based on a plurality of indices calculated using forecast values ​​resulting from demand forecasts for each of a plurality of products or planned values ​​resulting from shipping plans, the plurality of indices including (i) a first indice representing the degree of deviation between the actual past sales values ​​of each product and the forecast values, and (ii) a second indice representing the results of a comparison between the forecast values ​​or the planned values ​​for each product for a certain future period and the expected sales values ​​for that period. The reception unit 12 receives a user's selection of the products displayed on the first display unit 11. The second display unit 13 displays an analysis result regarding demand for the product corresponding to the selection received by the reception unit 12.

[0015] (Effects of demand forecasting support device) As described above, the demand forecasting support device 1 is configured to include a first display unit 11 that displays information about products for which forecasts need to be revised based on a plurality of indices calculated using forecast values ​​resulting from demand forecasts for a plurality of products or planned values ​​resulting from shipping plans, the plurality of indices including (i) a first index indicating the degree of deviation between the actual past sales values ​​of each product and the forecast values, and (ii) a second index indicating a comparison result between the forecast values ​​or the planned values ​​for each product for a certain future period and the expected sales values ​​for that period, a reception unit 12 that receives a user's selection of the products displayed by the first display unit 11, and a second display unit 13 that displays an analysis result about the demand for the product corresponding to the selection received by the reception unit 12. Therefore, the demand forecasting support device 1 has the effect of enabling a user to efficiently review the forecast for each product.

[0016] (Flow of demand forecasting support method) The flow of the demand forecasting support method S1 will be described with reference to Fig. 2. Fig. 2 is a flow diagram showing the flow of the demand forecasting support method S1. As shown in Fig. 2, the demand forecasting support method S1 includes a first display process S11, a reception process S12, and a second display process S13.

[0017] In a first display process S11, at least one processor displays information indicating products for which a forecast needs to be revised based on a plurality of indexes calculated using forecast values ​​resulting from demand forecasts for each of a plurality of products or planned values ​​resulting from shipping plans, the plurality of indexes including (i) a first index representing the degree of deviation between actual past sales values ​​of each product and the forecast values, and (ii) a second index representing a comparison result between the forecast values ​​or planned values ​​for each product for a certain future period and expected sales values ​​for that period. In a reception process S12, the at least one processor accepts a user's selection of the products displayed in the first display process S11. In a second display process S13, the at least one processor displays an analysis result regarding demand for the product corresponding to the selection accepted in the reception process S12.

[0018] (Effects of demand forecasting support methods) As described above, the demand forecasting support method S1 includes a first display process S11 in which at least one processor displays information about products for which forecast revision is required based on a plurality of indices calculated using forecast values ​​resulting from demand forecasts for a plurality of products or planned values ​​resulting from shipping plans, the plurality of indices including (i) a first indice representing the degree of deviation between actual past sales of each product and the forecast value, and (ii) a second indice representing a comparison result between the forecast value or the planned value for each product for a future period and the expected sales value for that period; a reception process S12 in which the at least one processor receives a user's selection of the products displayed in the first display process S11; and a second display process S13 in which the at least one processor displays an analysis result of demand for the product corresponding to the selection received by the reception process S12. Therefore, the demand forecasting support method S1 provides the advantage of enabling users to efficiently revise the forecast for each product.

[0019] Second Exemplary Embodiment A second exemplary embodiment, which is one example of an embodiment of the present invention, will be described in detail with reference to the drawings. Components having the same functions as those described in the above exemplary embodiment will be assigned the same reference numerals, and their description will be omitted as appropriate. The scope of application of each technology employed in this exemplary embodiment is not limited to this exemplary embodiment. That is, each technology employed in this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical hindrance occurs. Furthermore, each technology shown in each drawing referenced to explain this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical hindrance occurs.

[0020] (Overall flow of forecast and plan accuracy control operations) A demand forecasting support system 100A (see FIG. 4) according to the present disclosure is a system for managing the accuracy of demand forecasts for multiple products. Here, an overview of the forecast / plan accuracy management operation using the demand forecasting support system 100A will be described with reference to FIG. 3. FIG. 3 is a diagram showing an example of the outline of the forecast / plan accuracy management operation according to the present disclosure. First, in step S101, the demand forecasting system uses a forecasting model to make demand forecasts for multiple products. Based on the results of the demand forecast, a planner or the like generates a demand plan in step S102.

[0021] In step S103, the demand forecast support system 100A (see FIG. 4) manages the accuracy of the demand forecast based on the demand plan. In step S104, the demand forecast support system 100A outputs an alert for products that require a revision of the forecast based on the demand plan. In step S105, the planner or the like reviews the forecast model based on the analysis results of the forecast accuracy, and in step S106, performs a market interpretation based on the analysis results of the forecast accuracy. In step S107, the planner or the like reviews the demand plan based on the analysis results of the forecast accuracy and reflects the review results in the demand plan. In step S108, the planner or the like performs a demand review based on the results of the market interpretation and the review of the demand plan, and performs a sales and operations planning (S&OP) based on the results of the demand review.

[0022] 3, the demand forecasting system that performs step S101 may be the same system as the demand forecasting support system 100A that performs steps S103 and S104, or may be a different system. Furthermore, at least one of the above-mentioned steps S102, S105, S106, S107, and S108 may be performed by the demand forecasting system or the demand forecasting support system 100A.

[0023] (Configuration of demand forecasting support system) The configuration of a demand forecast support system 100A according to the present disclosure will be described with reference to FIG. 4. FIG. 4 is a block diagram showing the configuration of the demand forecast support system 100A. The demand forecast support system 100A is a system that manages the accuracy of demand forecasts and demand plans. The demand forecast support system 100A includes an information processing device 1A and a user terminal 2A. The information processing device 1A and the user terminal 2A are communicatively connected via a communication line N. The specific configuration of the communication line N does not limit the present embodiment, but examples of the communication line include a wireless LAN (Local Area Network), a wired LAN, a WAN (Wide Area Network), a public line network, a mobile data communication network, or a combination thereof.

[0024] The information processing device 1A is a device that provides various services related to the accuracy of demand forecasting, and is, for example, a general-purpose server. The information processing device 1A may also be a personal computer such as a laptop computer or a tablet terminal. The user terminal 2A is a terminal used by a user (e.g., a planner) who uses the above-mentioned service, and is, for example, a personal computer such as a laptop computer or a tablet terminal.

[0025] (Configuration of information processing device) The configuration of the information processing device 1A will be described with reference to Fig. 5. Fig. 5 is a block diagram showing the configuration of the information processing device 1A. The information processing device 1A includes a control unit 10A, a storage unit 20A, a communication unit 30A, an input unit 40A, and an output unit 50A. The communication unit 30A communicates with devices external to the information processing device 1A (such as a user terminal 2A) via a communication line. The communication unit 30A transmits data supplied from the control unit 10A to other devices, and supplies data received from other devices to the control unit 10A.

[0026] (Input / Output) The input unit 40A is configured to receive input to the information processing device 1A, and includes, for example, input devices such as a keyboard, mouse, touch panel, camera, and microphone. The input unit 40A may also be configured to receive data from the input devices via an interface such as a USB (Universal Serial Bus). The output unit 50A is configured to perform output from the information processing device 1A, and includes, for example, output devices such as a display, printer, touch panel, and speaker. The output unit 50A may also be configured to include, for example, an interface such as a USB, and output data to the output device via the interface.

[0027] (Storage part) The storage unit 20A stores various types of information referenced by the control unit 10A. Examples of such information include a database DB1, prediction accuracy information 201, and metrics analysis results 202.

[0028] (Database) Database DB1 stores information indicating product names, identification information, sales records, demand forecasts, brand types, category types, channel types, etc. Hereinafter, brands, categories, channels, etc. will also be referred to as "classifications."

[0029] (Prediction accuracy information) The forecast accuracy information 201 is information that indicates the accuracy of demand forecasts for multiple products. Examples of the forecast accuracy information 201 include MAPE (Mean Absolute Percentage Error), f-Bias (Forecast-Bias) ratio, and FVA (Forecast Value Added). However, the forecast accuracy information 201 is not limited to these.

[0030] (MAPE) MAPE is information that indicates the error rate of a demand forecast relative to actual sales of a product, and is used as an index for evaluating forecast accuracy. As an example, MAPE is the average of the absolute values ​​of the difference between the predicted and actual demand values ​​for each product, divided by the actual values. Here, the actual values ​​are values ​​that represent actual sales, such as the actual sales amount or the actual number of units sold. The forecast values ​​are values ​​that represent the results of demand forecasting, such as the predicted sales amount or the predicted number of units sold.

[0031] n items p1, p2,…p n (n is a natural number equal to or greater than 1) is calculated by the following formula (1): i is product p i is the actual sales value for the period covered by ^y i is product p i The forecast value of demand for the target period is "^y i " is expressed as "y with a hat i " means "

number

[0032] (weighted MAPE) Furthermore, the MAPE is not limited to the above formula (1), but may be information obtained from a value obtained by weighting the error rate of each product in the demand forecast against the actual sales performance of the product according to the actual sales performance of the product. Such MAPE will be referred to as "weighted MAPE" or "WAPE" below. n As an example, the weighted MAPE (WAPE) is calculated by the following equation (2):

number

[0033] Fig. 6 is a diagram showing an example of calculating the weighted MAPE. In the example of Fig. 6, the absolute error rate and weight value for each product in January are calculated from the actual values ​​and predicted values ​​for products A, B, and C in January, and the absolute error rate and weight value for each product in February are calculated from the actual values ​​and predicted values ​​for products A, B, and C in February. Furthermore, the sum of the products of the absolute error rate and weight value for each product in January is calculated as the weighted MAPE for January, and the sum of the products of the absolute error rate and weight value for each product in February is calculated as the weighted MAPE for February.

[0034] (f-Bias rate) The f-Bias rate is information that shows the tendency of error between forecast and plan. The f-Bias rate shows logic habits or market changes. n products p1, p2, ... p n For example, the f-Bias rate is calculated using the following formula (3). In formula (3), y i is product p i is the actual sales value for the period covered by ^y i is product p i This is the forecast value of demand for the target period.

number

[0035] Fig. 7 is a diagram showing an example of calculating the f-Bias rate. In the example of Fig. 7, the f-Bias rate for January is calculated from the actual and predicted values ​​for products A, B, and C in January, and the f-Bias rate for February is calculated from the actual and weighted values ​​for each product in February.

[0036] (FVA) FVA is an index that evaluates the added value of demand forecasts on a monetary basis. FVA is the forecast added value, and is information that measures whether the forecast results are creating value by comparing them with simple forecasts. For n products p1, p2, ...p n (n is a natural number equal to or greater than 1) is calculated by the following formula (4). i,k is product p i is the actual sales value for the target period k, and yi,k-1 is product p i This is the actual sales value for the period k-1 prior to the target period k. i,k is product p i is the forecast value of demand for the target period k. i is product p i is the unit price.

number

[0037] Fig. 8 is a diagram showing an example of FVA calculation. In the example of Fig. 8, the FVA for January and the FVA for February are calculated from the actual values ​​for products A, B, and C from December to February and the predicted values ​​for January to February. However, the comparison of the FVA prediction is not limited to the actual results for the previous month. The FVA may be calculated, for example, by comparing with the actual results for the previous year, or by comparing with a moving average.

[0038] (Metrics analysis results) Metrics analysis refers to the process of examining all of the following data together, in order to properly analyze the factors behind forecast errors (various metrics): trends in sales and composition ratios by channel, comparisons with the previous year and the year before, and comparisons with final consumption, wholesale shipments, and manufacturer shipments. Metrics analysis results are the results of analyzing various information related to demand forecasts for each product.

[0039] (Control unit) The control unit 10A includes a reception unit 11A and a display control unit 12A. The reception unit 11A is an example of a reception means according to the present disclosure. The display control unit 12A is an example of a first display means and a second display means.

[0040] (Reception Department) The reception unit 101A receives various instructions or selections from the user. For example, the reception unit 101A receives data indicating the user's instruction or selection from the user terminal 2A, thereby receiving the instruction or selection. The reception unit 101A may also receive an instruction or selection input by the user to the input unit 40A.

[0041] (Display control unit) The display control unit 12A outputs data representing various screens to a display and causes the screens to be displayed on the display. One example of the display is the display of the user terminal 2A. In this case, the display control unit 12A transmits the data representing various screens to the user terminal 2A via the communication unit 30A and causes the screens to be displayed on the display of the user terminal 2A. In this specification, the display control unit 12A transmitting data representing a screen to the user terminal 2A and displaying the screen on the display of the user terminal 2A is also referred to as "the display control unit 12A displaying the screen."

[0042] Furthermore, the display control unit 12A may output data representing a screen to a display connected to the output unit 50A, thereby causing the display to display the screen.

[0043] Fig. 9 is a diagram showing an overview of screen transitions displayed on the display by the display control unit 12A. In the example of Fig. 9, the display control unit 12A displays an overall summary screen SC11, a brand / category information screen SC12, a MAPE impact list screen SC13, a product-specific metrics analysis screen SC14, an alert screen SC15, a forecast value aggregation screen SC16, a forecast value review screen SC17, and a prediction process model review screen SC18.

[0044] (Overall summary screen) The overall summary screen SC11 is a screen that displays an overall summary of services provided by the information processing device 1A. Fig. 10 is a diagram showing an example of the overall summary screen SC11. In the example of Fig. 10, the overall summary screen SC11 includes a menu area A11, a graph display area A12, a setting area A13, and a table display area A14.

[0045] The menu area A11 includes buttons B11 to B16. The buttons B11 to B16 are buttons for transitioning to an overall summary screen SC11, a category-specific information screen SC12, a MAPE impact list screen SC13, a product-specific metrics analysis screen SC14, an alert screen SC15, and a forecast value aggregation screen SC16, respectively. When the user performs an operation to select one of the buttons B11 to B16, the display control unit 12A displays the screen corresponding to the selected button on the display.

[0046] The graph display area A12 is an area for displaying information indicating the accuracy of the demand forecast. As an example, the display control unit 12A displays a graph indicating the transition of MAPE for a certain month in the graph display area A12. In the example of Fig. 10, in the graph displayed in the graph display area A12, the horizontal axis indicates the date and time, and the vertical axis indicates MAPE.

[0047] The setting area A13 includes pull-down lists L11 to L14 for the user to select a product category. The pull-down lists L11 to L14 are pull-down lists for specifying "brand," "category," "channel," and "container axis," respectively. When the user selects a category using one of the pull-down lists L11 to L14, the display control unit 12A displays information indicating the accuracy of the demand forecast for products belonging to the selected category in the graph display area A12.

[0048] The table display area A14 is an area for displaying the demand forecast and actual results for multiple products belonging to a category selected by the user. In the example of Fig. 10, the display control unit 12A displays the target accuracy, prediction accuracy, predicted value, and actual value for each of the products A to E in the table display area A14.

[0049] Fig. 11 is a diagram showing another example of a graph displayed on the overall summary screen SC11. In the example of Fig. 11, graph G12 is a graph showing the accuracy of the demand forecast, with the horizontal axis showing MAPE and the vertical axis showing the f-Bias rate. The bubble size also shows FVA. Graph G13 is a graph showing the actual and target values ​​of MAPE for each of businesses A, B, and C.

[0050] FIG. 12 is a diagram showing other examples of graphs displayed on the overall summary screen SC11. In the example of FIG. 12, graphs G14 to G19 are graphs showing the accuracy of demand forecasting. In graph G14, the horizontal axis shows WAPE, and the vertical axis shows the f-Bias rate. The bubble size also shows the sales scale of each segment. In graph G15, the horizontal axis shows WAPE, and the vertical axis shows FVA. The bubble size also shows the sales scale of each segment. Graph G16 is a histogram of error rates. Graph G17 is a graph showing the target accuracy and current WAPE for each segment. Graph G18 is a graph showing the f-Bias rate for each segment. Graph G19 is a graph showing the FVA for each segment.

[0051] (Information screen for each brand and category) The responsible brand / category information screen SC12 includes a plurality of pieces of information indicating the accuracy of the demand forecast for a plurality of products belonging to a category specified by the user. In other words, the display control unit 12A displays a plurality of pieces of information indicating the accuracy of the demand forecast for a plurality of products belonging to a category specified by the user on the responsible brand / category information screen SC12. Examples of information indicating the accuracy of the demand forecast for a product include MAPE, weighted MAPE, f-Bias ratio, and FVA. In other words, the display control unit 12A can also display MAPE, f-Bias ratio, and FVA on the responsible brand / category information screen SC12. Here, the displayed MAPE may be weighted MAPE. However, the information indicating the accuracy of the demand forecast for a product is not limited to the above-described examples.

[0052] 13 is a diagram showing an example of the responsible brand / category information screen SC12. When the user selects button B12 on the overall summary screen SC11 of FIG. 10, the display control unit 12A transitions the displayed screen from the overall summary screen SC11 to the responsible brand / category information screen SC12. In the example of FIG. 13, the responsible brand / category information screen SC12 includes a menu area A11, accuracy information display areas A21 to A23, and a setting area A24. The menu area A11 is the same as the menu area A11 included in the overall summary screen SC11 of FIG. 10.

[0053] The accuracy information display areas A21 to A23 are areas for displaying graphs of MAPE, f-Bias rate, and FVA, respectively. The display control unit 12A displays, in the accuracy information display areas A21 to A23, the MAPE, f-Bias rate, and FVA, which represent the accuracy of the demand forecast for products belonging to a category specified by the user using the pull-down lists L11 to L14 in the setting area A24.

[0054] The setting area A24 includes pull-down lists L21 to L24 for the user to select a product category. The pull-down lists L21 to L24 are pull-down lists for specifying "brand," "channel," "container axis," and "display past years," respectively. When the user selects a category using one of the pull-down lists L21 to L24, the display control unit 12A displays the accuracy information of the products belonging to the selected category in the accuracy information display areas A21 to A23.

[0055] The menu area A11 includes buttons B11 to B16. The buttons B11 to B16 are buttons for transitioning to an overall summary screen SC11, a category-specific information screen SC12, a MAPE impact list screen SC13, a product-specific metrics analysis screen SC14, an alert screen SC15, and a forecast value aggregation screen SC16, respectively. When the user selects one of the buttons B11 to B16, the display control unit 12A displays the screen corresponding to the selected button. In particular, when the user selects button B13, the display control unit 12A displays the MAPE impact list screen SC13. In other words, the reception unit 11A can also be said to receive an instruction to display the forecast accuracy for each product on the responsible brand / category-specific information screen SC12.

[0056] Figure 14 shows another example of a graph displayed in the accuracy information display areas A21 to A23 of the brand / category information screen SC12. In the example of Figure 14, graph G22 shows the accuracy of the demand forecast, with the horizontal axis representing MAPE and the vertical axis representing the f-Bias rate. The displayed bubble size indicates the FVA.

[0057] FIG. 15 shows another example of a graph displayed on the brand / category information screen SC12. In the example of FIG. 15, graphs G24 to G29 are graphs showing the accuracy of demand forecasts for each division, such as brand or category. In graph G24, the horizontal axis shows WAPE, and the vertical axis shows the f-Bias rate. The bubble size also shows the sales scale of each segment. In graph G25, the horizontal axis shows WAPE, and the vertical axis shows FVA. The bubble size also shows the sales scale of each segment. Graph G26 is a histogram of error rates. Graph G27 is a graph showing the target accuracy and current WAPE for each brand. Graph G28 is a graph showing the f-Bias rate for each brand. Graph G29 is a graph showing the FVA for each brand.

[0058] (MAPE Impact List screen) The MAPE impact list screen SC13 includes a list of products based on MAPE impact. Here, MAPE impact is an index obtained by multiplying the absolute value of the error rate of the demand forecast for each product by the weight value for each product. More specifically, the MAPE impact is, for example, the value obtained by multiplying the absolute error rate for each product (the difference between the forecasted and actual sales values ​​divided by the actual sales values) by the weight value for each product. For example, the weight value is a value determined by the actual sales value of the product. The larger the sales scale and the larger the error for a product, the larger the MAPE impact value. The MAPE impact identifies products with large forecast accuracy errors and sales scales, making it possible to identify products for which demand forecast revisions should be prioritized.

[0059] In other words, when the reception unit 11A receives an instruction to display the MAPE impact list screen, the display control unit 12A can display information on the MAPE impact list screen SC13 indicating products that are likely to require a revision of their forecasts based on the MAPE impact for each of the multiple products belonging to the category specified by the user.

[0060] More specifically, the MAPE impact list is a list in which multiple products are sorted in descending order of MAPE impact. In other words, the display control unit 12A can also display a list in which multiple products are sorted in descending order of MAPE impact.

[0061] 16 is a diagram showing an example of the MAPE impact list screen SC13. When the user selects button B13 on the responsible brand / category information screen SC12 shown in FIG. 13, the display control unit 12A transitions the display from the responsible brand / category information screen SC12 to the MAPE impact list screen SC13. In the example of FIG. 16, the MAPE impact list screen SC13 includes a menu area A11, a list display area A31, and a setting area A32. The menu area A11 is the same as the menu area A11 included in the overall summary screen SC11 of FIG. 10. Furthermore, the setting area A24 is the same as the setting area A24 included in the responsible brand / category information screen SC12 of FIG. 13.

[0062] The list display area A31 is an area where a list of products sorted by MAPE impact is displayed. In the example of FIG. 16, the list display area A31 displays multiple records in which the following fields are associated with each other: "Product," "MAPE Impact," "TS," "Actual Results," and "Attributes." Of these fields, the "Product" field displays information that identifies the product (e.g., product name, product ID, etc.), and the "MAPE Impact" field displays the MAPE impact of the product. The "TS" field displays the TS (tracking signal) of the product. A method for calculating TS will be described later. The "Actual Results" field displays information representing the sales performance of the product. The "Attributes" field displays information representing the attributes of the product. If the user selects a field other than MAPE Impact in the list displayed in the list display area A31, the products may be sorted by the value of the selected field and the results may be displayed.

[0063] On the MAPE impact list screen SC13, the reception unit 11A receives the selection of a product included in the list of products sorted by MAPE impact. When the user selects a product from the list, the display control unit 12A displays a product-specific metrics analysis screen SC14 for the selected product.

[0064] FIG. 17 is a diagram showing another example of the MAPE impact list screen SC13. In the example of FIG. 17, the MAPE impact list screen SC13b includes a list display area A33 and a word cloud display area A34. The list display area A33 displays a list of products sorted by MAPE impact. In the example of FIG. 17, the list display area A33 displays multiple records in which the following fields are associated with each other: "Name," "MAPE Impact List," "TS," "Average Performance Value," "Average Performance Value Previous Month," and "Attributes." Of these fields, the "Name" field displays the name of the product. The "MAPE Impact List" field displays the MAPE impact of the product. The "TS" field displays the TS of the product. The "Average Performance Value" field displays information indicating the product's performance this month. The "Average Performance Value Previous Month" field displays information indicating the product's performance in the previous month.

[0065] In the word cloud display area A34, elements that are frequently listed as attributes of products with high MAPE impacts are extracted and displayed. That is, in this example, the display control unit 12A extracts product attributes whose MAPE impacts satisfy a predetermined condition (e.g., the ranking when sorted by MAPE impact is within a predetermined threshold) and displays the extracted attributes. At this time, the display control unit 12A may select and display the attribute that has been extracted the most times (the number of products having that attribute) from among the multiple extracted attributes. Furthermore, the display control unit 12A may highlight the attribute that has been extracted the most times (for example, by increasing the font size the more times).

[0066] (Product metrics analysis screen) The commodity-specific metrics analysis screen SC14 includes metrics analysis results for each commodity. As an example, the commodity-specific metrics analysis screen SC14 is a screen transitioned to from the MAPE impact list screen SC13 of FIG. 16 or an alert screen SC15 described later, based on a user instruction. When transitioning from the MAPE impact list screen SC13 of FIG. 16, the display control unit 12A can also display the analysis results regarding the demand for the commodity corresponding to the selection accepted by the reception unit 11A. Also, when transitioning from the alert screen SC15, the display control unit 12A can also display the analysis results regarding the demand for the commodity corresponding to the selection accepted by the reception unit 11A on the alert screen SC15.

[0067] Fig. 18 is a diagram showing an example of a product-specific metrics analysis screen SC14. When a user selects one of the products included in the list on the MAPE impact list screen SC13 in Fig. 16, the display control unit 12A transitions the display from the MAPE impact list screen SC13 to a product-specific metrics analysis screen SC14. In the example of Fig. 18, the product-specific metrics analysis screen SC14 includes a metrics analysis display area A41, a setting area A42, a memo area A43, and a menu area A44.

[0068] The metrics analysis display area A41 is an area that displays the metrics analysis results. In the example of FIG. 18, the metrics analysis display area A41 includes areas A411 to A412. Area A411 displays graphs that show changes in multiple pieces of information that indicate the accuracy of demand forecasting for a product specified by the user. Specifically, in the example of FIG. 18, graphs are displayed for the absolute error number, MAD (mean absolute error), RMSE (mean squared error), AVEDEV (mean absolute deviation), and MAPE impact. In the graphs displayed in area A411, the horizontal axis indicates the date and time, and the vertical axis indicates the value of the accuracy information (absolute error number, etc.).

[0069] Area A412 displays a graph showing changes in the f-Bias rate and tracking signal for the product specified by the user. In the graph displayed in area A412, the horizontal axis indicates the date and time, and the vertical axis indicates the value of each piece of information. The graph displayed in area A412 allows users to understand changes in demand and the habits of staff members.

[0070] Area A413 displays a graph showing changes in the composition ratio of shipments by week / channel for the product specified by the user. Area A414 displays a graph showing changes in shipments by week / channel compared to the previous year for the product specified by the user. In the graph in area A414, the horizontal axis shows the date and time, and the vertical axis shows the ratio (%).

[0071] The setting area A42 includes pull-down lists L41 to L45 that allow the user to select a product category. The pull-down lists L41 to L45 are pull-down lists for specifying "Brand," "Channel," "Container Axis," "Past Years to Display," and "Shipping Destination," respectively. When the user selects a category using one of the pull-down lists L41 to L44, the display control unit 12A displays the metrics analysis results for the products belonging to the selected category in the graph display area A12. The memo area A43 displays text entered by the person in charge of the product, etc.

[0072] The menu area A44 includes buttons B11 to B17. The buttons B11 to B16 are buttons for transitioning to an overall summary screen SC11, a category-specific information screen SC12, a MAPE impact list screen SC13, a product-specific metrics analysis screen SC14, an alert screen SC15, and a forecast value aggregation screen SC16, respectively. The button B17 is a button for transitioning to a prediction process model review screen SC18. When the user selects one of the buttons B11 to B17, the display control unit 12A displays the screen corresponding to the selected button on the display.

[0073] Figure 19 is a diagram showing other examples of graphs displayed on the product-specific metrics analysis screen SC14. In the example of Figure 19, graph G41 is a graph showing the transition of the error rate and tracking signal. Graph G42 is a graph showing the transition of monthly FVA and cumulative FVA. Graph G43 is a graph showing the year-on-year change in shipments and sales volume by channel. Graph G44 is a graph showing the year-on-year change in sales by distribution stage.

[0074] (Alert screen) The alert screen SC15 includes information indicating products that are the subject of an alert regarding a revision of the forecast based on the demand forecast results for multiple products. In other words, the display control unit 12A displays information indicating products that require a revision of the forecast based on multiple indicators calculated using forecast values ​​that are the results of the demand forecast for each of the multiple products or planned values ​​that are the results of the shipping plan.

[0075] (Example of an alert) Specific examples of alerts include (i) past alerts, (ii) TS alerts, (iii) future alerts, (iv) wholesale shipment change alerts, and (v) POS change alerts. The information processing device 1A visualizes products with a high correction priority by combining multiple alerts. This allows the user to efficiently review predictions for each product. The threshold used for each alert is set by the user based on, for example, the distribution of actual error rates and the evaluation of the person in charge. In this case, the reception unit 11A receives the threshold set by the user, and the display control unit 12A displays the products using the threshold set by the user.

[0076] (i) Past Alerts A past alert is an alert for a product whose past actual performance deviates from the plan. A past alert uses an index (an example of a first index) that indicates the degree of deviation between the past sales actual value of each product and the forecast value. For example, a past alert is issued for a product for which an index indicating the plan error rate for the previous month or the plan error rate for the previous week is greater than a threshold value. In this case, the display control unit 12A, for example, identifies a product that is the target of a past alert by comparing the plan error rate for the previous month, calculated using the actual performance value and the plan value for the previous month, with a threshold value. For example, the display control unit 12A may also identify a product that is the target of a past alert by comparing the plan error rate for the previous week, calculated using the actual performance value and the plan value for the previous week, with a threshold value.

[0077] (ii) TS Alert A TS (Tracking Signal) alert is an alert for products whose errors continue to skew in a specific direction. TS alerts use an index (an example of a third index) that shows the trend in the difference between predicted and actual values. Here, TS is the value obtained by dividing f-Bias by MAD (Mean Absolute Deviation). If TS continues to skew in the positive direction, it can be said that the risk of excess inventory is increasing, and if it continues to skew in the negative direction, it can be said that the risk of stockouts is increasing. By checking TS, for example, practitioners can make early revisions to demand forecasts and plans for each product.

[0078] As an example, a TS alert is sent for a product whose absolute value of TS over a four-week period is greater than a threshold value (e.g., "3.2"). In this case, as an example, the display control unit 12A identifies the product to be the target of the TS alert by comparing the TS calculated using the weekly planned value and the weekly actual value with the threshold value.

[0079] (iii) Future Alert A future alert is an alert based on the results of a comparison between a shipping plan or demand forecast for a certain future period and the latest expected arrival date for the same period. A future alert uses an index (an example of a second index) that represents the results of a comparison between the predicted value of the demand forecast or the planned value of the shipping plan for each product for a certain future period and the expected sales value for the same period. As an example, a future alert uses the difference rate between the shipping plan or demand forecast and the latest expected arrival date for the same period as an index, and is notified of products for which the index is greater than a threshold. In this case, the display control unit 12A, as an example, identifies products that are the subject of a future alert by comparing the difference rate with a threshold.

[0080] More specifically, the indicators used in future alerts are calculated from the expected arrival date for a certain period in the future (for example, up to three weeks ahead) and the shipping plan for the same period. The expected arrival date is calculated using the actual results (trends) for the same period of the previous year.

[0081] (iv) Wholesale shipment change alerts Wholesale shipment change alerts are alerts for products with large changes in wholesale shipments. Wholesale shipment change alerts use an indicator related to the trend in actual wholesale shipment values ​​(an example of a fourth indicator). As an example, wholesale shipment change alerts are issued for products whose rate of change in the moving average for a specific period or its year-on-year change is greater than a threshold. Examples of indicators for wholesale shipment change alerts include (a) an indicator obtained from the previous year's performance, and (b) an indicator obtained from the rate of change in the moving average. For products with previous year's performance, the indicator (a) above is used. On the other hand, for products without previous year's performance, the indicator (b) above is used.

[0082] When using the index (a) above, the display control unit 12A, for example, uses the moving average of performance values ​​for a specific period (e.g., the most recent week) divided by the moving average of performance values ​​for the same period of the previous year as an index, and identifies products for which the index is greater than a threshold as targets for an alert. Using a moving average can reduce the influence of noise, and using a year-on-year comparison can reduce the influence of seasonal factors. This makes trend changes more noticeable, making them easier to detect.

[0083] On the other hand, for products that have no sales results in the previous year, the indicator (a) cannot be used, and therefore the indicator (b) is used. In this case, the display control unit 12A, for example, uses the moving average of the sales results for a specific period (for example, the last three days) divided by the moving average of the sales results for the previous period (for example, the previous week) as an indicator, and identifies products for which the indicator is greater than a threshold as targets for an alert.

[0084] (v) POS change alerts POS change alerts are alerts for products with large changes in POS (Point of Sale). POS change alerts use an indicator related to the trend in actual consumption values ​​by end users (an example of a fourth indicator). As an example, POS alerts are issued for products where the rate of change in the moving average for a specific period or the year-on-year change is greater than a threshold. As with the wholesale shipment change alert described above, indicators for POS change alerts include (a) an indicator obtained from the previous year's performance, and (b) an indicator obtained from the rate of change in the moving average. For products with previous year's performance, the indicator (a) above is used. On the other hand, for products without previous year's performance, the indicator (b) above is used.

[0085] When using the index (a) above, the display control unit 12A, for example, uses the moving average of performance values ​​for a specific period (e.g., the most recent week) divided by the moving average of performance values ​​for the same period of the previous year as an index, and identifies products for which the index is greater than a threshold as targets for an alert. Using a moving average can reduce the influence of noise, and using a year-on-year comparison can reduce the influence of seasonal factors. This makes trend changes more noticeable, making them easier to detect.

[0086] On the other hand, for products that have no sales results in the previous year, the indicator (a) cannot be used, and therefore the indicator (b) is used. In this case, the display control unit 12A, for example, uses the moving average of the sales results for a specific period (for example, the last three days) divided by the moving average of the sales results for the previous period (for example, the previous week) as an indicator, and identifies products for which the indicator is greater than a threshold as targets for an alert.

[0087] FIG. 20 is a diagram showing an example of an alert screen SC15. In the example of FIG. 20, the alert screen SC15 includes a menu area A11 and an alert display area A51. The alert display area A51 displays a list of products that are the subject of the alert. In the example of FIG. 20, the alert display area A51 displays multiple records in which the following items are associated with each other: "Product," "Final deviation rate," "Last week's error rate," "TS," "Wholesale shipment moving average year-on-year change," and "POS moving average year-on-year change." The "Product" item displays information that identifies the product (e.g., product name, product ID, etc.). The "Final deviation rate" item displays the rate of difference between the latest shipping plan and short-term final forecast, which is an indicator of the above (iii) future alert.

[0088] The "Previous week error rate" field displays the previous week's planned error rate, which is an indicator of the above (i) past alert. The "TS" field displays TS, which is an indicator of the above (ii) TS alert. The "Wholesale shipment moving average year-on-year change" field displays the year-on-year change in the wholesale shipment moving average, which is an indicator of the above (iv) wholesale shipment change alert. The "POS moving average year-on-year change" field displays the year-on-year change in the POS moving average, which is an indicator of the above (v) POS change alert.

[0089] In the example of FIG. 20, multiple products are sorted and displayed in descending order of the landing deviation rate. At this time, products whose indicators in each alert are greater than the threshold are displayed more emphasized than other products (for example, by changing the color and increasing the font size). However, the alert screen SC15 is not limited to the example of FIG. 20. In the alert screen SC15, multiple products may be sorted and displayed in descending order of the indicators of alerts other than future alerts, for example.

[0090] Furthermore, on the alert screen SC15, the display control unit 12A may display a list of products sorted according to a sorting condition obtained by combining indicators of a plurality of alerts. For example, the display control unit 12A may display a list of products sorted in descending order of the integrated value of the indicator of a past alert and the indicator of a future alert.

[0091] Furthermore, the display control unit 12A may extract and display products whose indexes exceed a threshold from among multiple products. In this case, the display control unit 12A may display a list of products based on an index that combines multiple types of alerts. For example, the display control unit 12A may display on the alert screen SC15 products that satisfy all of the following conditions (1) to (3): (1) the absolute value of the landing deviation rate is 20% or more, (2) the absolute value of the previous week's error rate is 20% or more, and (3) the directions of the errors are all the same.

[0092] Furthermore, the display of the alert screen SC15 is not limited to a list display. For example, the display control unit 12A may display an image in which at least some of the multiple products are plotted in a feature space (two-dimensional space, three-dimensional space, etc.) determined by the indices of the multiple alerts. More specifically, for example, the display control unit 12A may display an image in which the multiple products are plotted in a three-dimensional space in which the indices of past alerts are the x-axis, the indices of future alerts are the y-axis, and the indices of TS alerts are the z-axis. In this case, the display control unit 12A may extract products from the multiple products whose indices satisfy a predetermined condition (for example, the indices are greater than a threshold value) and display an image in which the extracted products are plotted in the three-dimensional space. As another example, the display control unit 12A may display, for example, a radar chart of the multiple indices for each product.

[0093] While the alert display area A51 is displayed, the user can select a product from the list. In other words, on the alert screen SC15, the reception unit 11A receives the user's selection of a product displayed in the alert display area A51. When the user selects a product from the list, the display control unit 12A displays a product-specific metrics analysis screen SC14 for the selected product. In other words, the display control unit 12A displays the analysis results regarding the demand for the product corresponding to the received selection.

[0094] FIG. 21 is a diagram visually illustrating the characteristics of various alerts. As shown in the figure, TS alerts, past alerts, and future alerts are mechanisms for detecting products with large error rates in distribution inventory, while POS change alerts are mechanisms for detecting products with large error rates in final consumption. Also, TS alerts, wholesale shipment change alerts, and POS alerts are mechanisms for detecting products with consistently large error rates, while past alerts and future alerts are mechanisms for detecting products with large recent error rates. Thus, TS alerts, past alerts, future alerts, wholesale shipment change alerts, and POS change alerts each have different characteristics. By combining multiple alerts, the information processing device 1A can more efficiently identify products for which forecasts should be revised as a priority.

[0095] (Prediction process model review screen) 22 is a diagram showing an example of the prediction process model review screen SC18. When the user selects button B17 on the product-specific metrics analysis screen SC14, the display control unit 12A transitions the displayed screen from the product-specific metrics analysis screen SC14 to the prediction process model review screen SC18.

[0096] In the example of FIG. 22, the prediction process model review screen SC18 includes a menu area A11, a graph display area A81, a setting area A82, and a table display area A83.

[0097] A graph showing changes in FVA and measurement error (scaled error) is displayed in the graph display area A81. In the graph displayed in the graph display area A81, the horizontal axis indicates the date and time, and the vertical axis indicates FVA or measurement error.

[0098] The setting area A82 includes a pull-down list L82 that allows the user to select the number of years to be displayed. The pull-down list L82 is a pull-down list for specifying the "number of past years to display." When the user selects a period included in the list in the pull-down list L81, the display control unit 12A displays a graph representing the FVA and measurement error for the selected period in the graph display area A81.

[0099] The table display area A83 displays information indicating the prediction accuracy obtained from each of a plurality of prediction models.

[0100] (User terminal configuration) 23 is a block diagram showing the configuration of the user terminal 2A. The user terminal 2A includes a control unit 210A, a storage unit 220A, a communication unit 230A, an input unit 240A, and an output unit 250A. The user terminal 2A is, for example, a general-purpose computer. The storage unit 220A stores various types of information referenced by the control unit 210A. The communication unit 230A communicates with devices external to the user terminal 2A (such as the information processing device 1A) via a communication line N.

[0101] (Input / Output) The input unit 240A is configured to receive input to the user terminal 2A, and includes, for example, input devices such as a keyboard, mouse, touch panel, camera, and microphone. The input unit 240A may also be configured to receive data from the input devices via an interface such as USB. The output unit 250A is configured to perform output from the user terminal 2A, and includes, for example, output devices such as a display, printer, touch panel, and speaker. The output unit 250A may also be configured to include, for example, an interface such as USB, and to output data to the output device via the interface.

[0102] (Control unit) The control unit 210A includes an application execution unit 21A. The application execution unit 21A is realized by the control unit 210A reading and executing instructions of an application program stored in the storage unit 220A. The application execution unit 21A executes the application program stored in the storage unit 220A, and performs processing to transmit information representing the shape, material, and molding conditions of a molded body that is the object to be molded to the information processing device 1A, and processing to display simulation results of the molded body. An application implemented by the application execution unit 21A is, for example, a general-purpose web browser, but is not limited to this. The application execution unit 21A may also be a dedicated application that communicates with the information processing device 1A to support the design of a molded body.

[0103] The application execution unit 21A includes a reception unit 211A and a display control unit 212A. The reception unit 211A receives user specifications, selections, etc. The display control unit 212A displays various screens on the display based on data received from the information processing device 1A.

[0104] (Flow of demand forecasting support method) 24 and 25 are sequence diagrams showing an example of the flow of a demand forecasting support method executed by the information processing device 1A. In the example of Fig. 24, a case will be described in which various screens are displayed on the display of the user terminal 2A. When the user of the user terminal 2A performs an operation to start an application using an input device, in step S101, the application execution unit 21A sends a request for an overall summary screen SC11 to the information processing device 1A.

[0105] When the information processing device 1A receives the request from the user terminal 2A, in step S102, the display control unit 12A transmits data representing the overall summary screen SC11 to the user terminal 2A. In step S103, the user terminal 2A displays the overall summary screen SC11 on the display based on the received data.

[0106] While the overall summary screen SC11 is displayed on the display, the user can perform various operations such as selecting a button displayed in the menu area A11. For example, when the button B12 is selected on the overall summary screen SC11 in Fig. 10, in step S104, the application execution unit 21A transmits a request for the brand / category information screen SC12 corresponding to the selected button B12 to the information processing device 1A.

[0107] When the information processing device 1A receives the request from the user terminal 2A, in step S105, the display control unit 12A transmits data representing the responsible brand / category information screen SC12 to the user terminal 2A. In step S106, the user terminal 2A displays the responsible brand / category information screen SC12 on its display based on the data received from the information processing device 1A. The responsible brand / category information screen SC12 displays multiple graphs representing the accuracy of demand forecasts, such as MAPE, f-Bias rate, and FVA, as shown in FIG. 13.

[0108] While the responsible brand / category information screen SC12 is displayed on the display, the user can perform various operations such as selecting a button displayed in the menu area A11. For example, when button B13 is selected on the responsible brand / category information screen SC12 in Fig. 13, in step S107, the application execution unit 21A transmits a request for the MAPE impact list screen SC13 corresponding to the selected button B13 to the information processing device 1A.

[0109] When the information processing device 1A receives the request from the user terminal 2A, in step S108, the display control unit 12A transmits data representing a MAPE impact list screen SC13 to the user terminal 2A. In step S109, the user terminal 2A displays the MAPE impact list screen SC13 on the display based on the data received from the information processing device 1A. In other words, when the reception unit 11A receives an instruction to display the prediction accuracy for each product (step S107), the display control unit 12A displays on the display a list of products that are likely to require a revision of the prediction based on the MAPE impact for each of the multiple products belonging to the specified category (steps S108 and S109).

[0110] While the MAPE impact list screen SC13 is displayed on the display, the user can perform various operations such as selecting a product included in the list. For example, when one of the products included in the list is selected on the MAPE impact list screen SC13 of Fig. 16, in step S110, the application execution unit 21A transmits data indicating the selected product to the information processing device 1A.

[0111] When the information processing device 1A receives the above data from the user terminal 2A, in step S111, the display control unit 12A transmits data representing the metrics analysis results for each product to the user terminal 2A. In step S112, the user terminal 2A displays the metrics analysis results on a display based on the data received from the information processing device 1A.

[0112] Fig. 25 is a sequence diagram showing another example of the flow of the demand forecasting support method executed by the information processing device 1A. The processing of steps S101 to S103 in Fig. 25 is the same as the processing of steps S101 to S103 in Fig. 24. When button B15 is selected on the overall summary screen SC11 in Fig. 10, in step S201, the application execution unit 21A sends a request for an alert screen SC15 corresponding to the selected button B15 to the information processing device 1A.

[0113] When the information processing device 1A receives the request from the user terminal 2A, in step S202, the display control unit 12A transmits data representing the alert screen SC15 to the user terminal 2A. In step S203, the user terminal 2A displays the alert screen SC15 on the display based on the data received from the information processing device 1A.

[0114] While the alert screen SC15 is displayed on the display, the user can perform various operations such as selecting a product included in the list. For example, when one of the products included in the list is selected on the alert screen SC15 of Fig. 20, in step S204, the application execution unit 21A transmits data indicating the selected product to the information processing device 1A.

[0115] When the information processing device 1A receives the above data from the user terminal 2A, in step S205 the display control unit 12A transmits data representing the metrics analysis results for each product to the user terminal 2A. In step S206, the user terminal 2A displays the metrics analysis results on a display based on the data received from the information processing device 1A. In other words, the display control unit 12A displays a list of products that are the subject of an alert regarding a forecast review, and when the reception unit 11A receives a selection of a product included in the displayed list, the display control unit 12A displays the metrics analysis results for the product corresponding to the received selection.

[0116] (Effects of information processing devices) As described above, the information processing device 1A employs a configuration in which the multiple indices used for alerts include TS (third index), which indicates the trend of the difference between the predicted value of the demand forecast and the actual value. Because TS is an index that indicates the trend of the difference between the predicted value and the actual value of the demand, by using the TS alert in combination with other alerts, the information processing device 1A can obtain the effect of more efficiently reviewing the forecast, taking into account continuous fluctuations in demand.

[0117] Furthermore, the information processing device 1A employs a configuration in which the multiple indicators used in the alerts include an indicator related to the trend in actual wholesale shipment values ​​(indicator for wholesale shipment change alert) or an indicator related to the trend in actual end-user consumption values ​​(indicator for POS change alert). Because wholesale shipment change alerts are alerts for products with large fluctuations in wholesale shipment values, by using wholesale shipment change alerts in combination with other alerts, the information processing device 1A can achieve the effect of more efficiently reviewing forecasts that take into account fluctuations in wholesale shipment values. Furthermore, because POS change alerts are alerts for products with large fluctuations in POS values, by using POS change alerts in combination with other alerts, the information processing device 1A can achieve the effect of more efficiently reviewing forecasts that take into account fluctuations in POS values.

[0118] Furthermore, the information processing device 1A employs a configuration in which the display control unit 12A displays a list of products sorted according to sorting conditions obtained by combining indicators of multiple alerts. By checking the displayed list, the user can efficiently identify products for which the forecast should be revised as a priority.

[0119] Furthermore, the information processing device 1A employs a configuration in which the display control unit 12A displays an image in which at least some of the multiple products are plotted in a feature space determined by the indicators of multiple alerts. By checking the displayed image, the indicators of each of the multiple products can be visually grasped, which advantageously allows the user to efficiently grasp the products for which the forecast should be prioritized.

[0120] Furthermore, the information processing device 1A is configured such that the display control unit 12A extracts and displays products whose alert indicators exceed a threshold from a plurality of products, and the reception unit 11A receives the threshold set by the user. Therefore, the information processing device 1A can provide a display that reflects the user's intention, and can provide an effect that makes it easier for the user to grasp products whose predictions should be revised.

[0121] [Software implementation example] Some or all of the functions of the demand forecasting support device 1, the information processing device 1A, and the user terminal 2A (hereinafter also referred to as "each of the above devices") may be realized by hardware such as an integrated circuit (IC chip), or by software.

[0122] In the latter case, each of the above devices is realized by, for example, a computer that executes instructions of a program, which is software that realizes each function. An example of such a computer (hereinafter referred to as computer C) is shown in Figure 26. Figure 26 is a block diagram showing the hardware configuration of computer C that functions as each of the above devices.

[0123] The computer C includes at least one processor C1 and at least one memory C2. The memory C2 stores a program P for causing the computer C to operate as each of the above-mentioned devices. In the computer C, the processor C1 reads and executes the program P from the memory C2, thereby realizing the functions of each of the above-mentioned devices.

[0124] The processor C1 may be, for example, a central processing unit (CPU), a graphic processing unit (GPU), a digital signal processor (DSP), a micro processing unit (MPU), a floating point number processing unit (FPU), a physics processing unit (PPU), a tensor processing unit (TPU), a quantum processor, a microcontroller, or a combination thereof. The memory C2 may be, for example, a flash memory, a hard disk drive (HDD), a solid state drive (SSD), or a combination thereof.

[0125] The computer C may further include a RAM (Random Access Memory) for expanding the program P during execution and for temporarily storing various data. The computer C may also include a communication interface for transmitting and receiving data to and from other devices. The computer C may also include an input / output interface for connecting input / output devices such as a keyboard, mouse, display, and printer.

[0126] Furthermore, the program P can be recorded on a non-transitory tangible recording medium M that can be read by the computer C. Such a recording medium M can be, for example, a tape, a disk, a card, a semiconductor memory, or a programmable logic circuit. The computer C can acquire the program P via such a recording medium M. The program P can also be transmitted via a transmission medium. Such a transmission medium can be, for example, a communication network or broadcast waves. The computer C can also acquire the program P via such a transmission medium.

[0127] Furthermore, the functions of each of the devices may be realized by a single processor provided in a single computer, by multiple processors provided in a single computer working in cooperation, or by multiple processors provided in each of multiple computers working in cooperation. Furthermore, the programs for causing each of the devices to realize the functions may be stored in a single memory provided in a single computer, or may be distributed and stored in multiple memories provided in a single computer, or may be distributed and stored in multiple memories provided in each of multiple computers.

[0128] [Appendix 1] [Appendix A] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0129] (Appendix A1) a first display means for displaying information indicating products for which a forecast needs to be revised based on a plurality of indices calculated using forecast values ​​that are the result of a demand forecast for each of a plurality of products or planned values ​​that are the result of a shipping plan, the indices including: (i) a first indice that indicates the degree of deviation between the actual past sales value of each product and the forecast value; and (ii) a second indice that indicates the result of a comparison between the forecast value or the planned value for each product for a certain period in the future and the expected sales value for that period; a receiving means for receiving a user's selection of the product displayed by the first display means; a second display means for displaying an analysis result regarding the demand for the product corresponding to the selection accepted by the accepting means; A demand forecasting support device comprising:

[0130] (Appendix A2) the plurality of indexes includes a third index indicating a trend of a difference between the predicted value and the actual value; A demand forecasting support device according to Appendix A1.

[0131] (Appendix A3) The plurality of indicators include a fourth indicator relating to a change in actual wholesale shipment value or actual consumption value by end users; A demand forecasting support device according to appendix A1 or A2.

[0132] (Appendix A4) the second display means displays a list of products sorted according to sorting conditions obtained by combining the plurality of indexes. A demand forecasting support device according to any one of appendices A1 to A3.

[0133] (Appendix A5) the second display means displays an image in which at least some of the plurality of products are plotted in a feature space defined by the plurality of indexes. A demand forecasting support device according to any one of appendices A1 to A4.

[0134] (Appendix A6) the second display means extracts and displays products whose indexes exceed a threshold value from the plurality of products; the accepting means accepts the setting of the threshold value by a user; A demand forecasting support device according to any one of appendices A1 to A5.

[0135] [Appendix B] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0136] (Appendix B1) a first display process in which at least one processor displays information indicating products requiring a revision of the forecast based on a plurality of indices calculated using forecast values ​​resulting from demand forecasts for each of a plurality of products or planned values ​​resulting from shipping plans, the plurality of indices including (i) a first indice representing the degree of deviation between the actual past sales value of each product and the forecast value, and (ii) a second indice representing the result of a comparison between the forecast value or the planned value for each product in a certain future period and the expected sales value for that period; a receiving process in which the at least one processor receives a user's selection of the product displayed in the first display process; a second display process in which the at least one processor displays an analysis result regarding demand for the product corresponding to the selection received in the reception process; A demand forecasting support method including:

[0137] (Appendix B2) the plurality of indexes includes a third index indicating a trend of a difference between the predicted value and the actual value; A demand forecasting support method as described in Appendix B1.

[0138] (Appendix B3) The plurality of indicators include a fourth indicator relating to a change in actual wholesale shipment value or actual consumption value by end users; A demand forecasting support method according to Appendix B1 or B2.

[0139] (Appendix B4) the second display process displays a list of products sorted according to sorting conditions obtained by combining the plurality of indexes. A demand forecasting support method according to any one of appendices B1 to B3.

[0140] (Appendix B5) the second display process displays an image in which at least some of the plurality of products are plotted in a feature space determined by the plurality of indexes. A demand forecasting support method according to any one of appendices B1 to B4.

[0141] (Appendix B6) the second display process extracts and displays products whose indexes exceed a threshold value from the plurality of products; In the reception process, the at least one processor receives a setting of the threshold value by a user. A demand forecasting support method according to any one of appendices B1 to B5.

[0142] [Appendix C] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0143] (Appendix C1) A program for causing a computer to function as a demand forecasting support device, the program comprising: a first display means for displaying information indicating products for which a forecast needs to be revised based on a plurality of indices calculated using forecast values ​​that are the result of a demand forecast for each of a plurality of products or planned values ​​that are the result of a shipping plan, the indices including: (i) a first indice that indicates the degree of deviation between the actual past sales value of each product and the forecast value; and (ii) a second indice that indicates the result of a comparison between the forecast value or the planned value for each product for a certain period in the future and the expected sales value for that period; a receiving means for receiving a user's selection of the product displayed by the first display means; a second display means for displaying an analysis result regarding the demand for the product corresponding to the selection accepted by the accepting means; A demand forecasting support program that functions as a

[0144] (Appendix C2) the plurality of indexes includes a third index indicating a trend of a difference between the predicted value and the actual value; Demand forecasting support program described in Appendix C1.

[0145] (Appendix C3) The plurality of indicators include a fourth indicator relating to a change in actual wholesale shipment value or actual consumption value by end users; A demand forecasting support program as described in Appendix C1 or C2.

[0146] (Appendix C4) the second display means displays a list of products sorted according to sorting conditions obtained by combining the plurality of indexes. A demand forecasting support program according to any one of Appendices C1 to C3.

[0147] (Appendix C5) the second display means displays an image in which at least some of the plurality of products are plotted in a feature space defined by the plurality of indexes. A demand forecasting support program according to any one of Appendices C1 to C4.

[0148] (Appendix C6) the second display means extracts and displays products whose indexes exceed a threshold value from the plurality of products; the accepting means accepts the setting of the threshold value by a user; A demand forecasting support program according to any one of Appendices C1 to C5.

[0149] [Appendix D] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0150] (Appendix D1) at least one processor, a first display process for displaying information indicating products for which a forecast needs to be revised based on a plurality of indices calculated using forecast values ​​that are the result of demand forecasts for each of a plurality of products or planned values ​​that are the result of shipping plans, the indices including: (i) a first indice that indicates the degree of deviation between the actual past sales value of each product and the forecast value; and (ii) a second indice that indicates the result of comparing the forecast value or the planned value for each product for a certain future period with the expected sales value for that period; a receiving process for receiving a user's selection of the product displayed in the first display process; a second display process for displaying an analysis result regarding the demand for the product corresponding to the selection received in the reception process; A demand forecasting support device that executes the above.

[0151] The demand forecasting support device may further include a memory, and the memory may store a program for causing the at least one processor to execute each of the processes.

[0152] (Appendix D2) the plurality of indexes includes a third index indicating a trend of a difference between the predicted value and the actual value; A demand forecasting support device according to appendix D1.

[0153] (Appendix D3) The plurality of indicators include a fourth indicator relating to a change in actual wholesale shipment value or actual consumption value by end users; A demand forecasting support device according to appendix D1 or D2.

[0154] (Appendix D4) the second display process displays a list of products sorted according to sorting conditions obtained by combining the plurality of indexes. A demand forecasting support device according to any one of appendices D1 to D3.

[0155] (Appendix D5) the second display process displays an image in which at least some of the plurality of products are plotted in a feature space determined by the plurality of indexes. A demand forecasting support device according to any one of appendices D1 to D4.

[0156] (Appendix D6) the second display process extracts and displays products whose indexes exceed a threshold value from the plurality of products; In the reception process, the at least one processor receives a setting of the threshold value by a user. A demand forecasting support device according to any one of appendices D1 to D5.

[0157] [Appendix E] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0158] (Appendix E1) A program that causes a computer to function as a demand forecasting support device, The computer, a first display process for displaying information indicating products for which a forecast needs to be revised based on a plurality of indices calculated using forecast values ​​that are the result of demand forecasts for each of a plurality of products or planned values ​​that are the result of shipping plans, the indices including: (i) a first indice that indicates the degree of deviation between the actual past sales value of each product and the forecast value; and (ii) a second indice that indicates the result of comparing the forecast value or the planned value for each product for a certain future period with the expected sales value for that period; a receiving process for receiving a user's selection of the product displayed in the first display process; a second display process for displaying an analysis result regarding the demand for the product corresponding to the selection received in the reception process; A non-transitory recording medium on which a demand forecasting support program for executing the above is recorded. [Explanation of symbols]

[0159] 1. Demand forecasting support device 11 1st display section 12 Reception 13 Second display section 1A Information processing equipment 2A User terminal 10A, 210A control unit 11A, 101A, 211A Reception 12A, 212A Display control unit 20A, 220A memory section 21A Application Execution Unit

Claims

1. a first display means for displaying information indicating products for which a forecast needs to be revised based on a plurality of indices calculated using forecast values ​​that are the result of a demand forecast for each of a plurality of products or planned values ​​that are the result of a shipping plan, the indices including: (i) a first indice that indicates the degree of deviation between the actual past sales value of each product and the forecast value; and (ii) a second indice that indicates the result of a comparison between the forecast value or the planned value for each product for a certain period in the future and the expected sales value for that period; a receiving means for receiving a user's selection of the product displayed by the first display means; a second display means for displaying an analysis result regarding the demand for the product corresponding to the selection accepted by the accepting means; A demand forecasting support device comprising:

2. the plurality of indexes includes a third index indicating a trend of a difference between the predicted value and the actual value; The demand forecasting support device according to claim 1.

3. the plurality of indicators includes a fourth indicator relating to a change in actual wholesale shipment value or actual consumption value by end users; The demand forecasting support device according to claim 1 or 2.

4. the second display means displays a list of products sorted according to sorting conditions obtained by combining the plurality of indexes. The demand forecasting support device according to claim 1 or 2.

5. the second display means displays an image in which at least some of the plurality of products are plotted in a feature space defined by the plurality of indexes. The demand forecasting support device according to claim 1 or 2.

6. the second display means extracts and displays products whose indexes exceed a threshold value from the plurality of products; the accepting means accepts the setting of the threshold value by a user; The demand forecasting support device according to claim 1 or 2.

7. a first display process in which at least one processor displays information indicating products requiring a revision of the forecast based on a plurality of indices calculated using forecast values ​​resulting from demand forecasts for each of a plurality of products or planned values ​​resulting from shipping plans, the plurality of indices including: (i) a first indice representing the degree of deviation between the actual past sales value of each product and the forecast value; and (ii) a second indice representing the result of a comparison between the forecast value or the planned value for each product in a certain future period and the expected sales value for that period; a receiving process in which the at least one processor receives a user's selection of the product displayed in the first display process; a second display process in which the at least one processor displays an analysis result regarding demand for the product corresponding to the selection received in the reception process; A demand forecasting support method including:

8. A program for causing a computer to function as a demand forecasting support device, the program comprising: a first display means for displaying information indicating products for which a forecast needs to be revised based on a plurality of indices calculated using forecast values ​​that are the result of a demand forecast for each of a plurality of products or planned values ​​that are the result of a shipping plan, the indices including: (i) a first indice that indicates the degree of deviation between the actual past sales value of each product and the forecast value; and (ii) a second indice that indicates the result of a comparison between the forecast value or the planned value for each product for a certain period in the future and the expected sales value for that period; a receiving means for receiving a user's selection of the product displayed by the first display means; a second display means for displaying an analysis result regarding the demand for the product corresponding to the selection accepted by the accepting means; A demand forecasting support program that functions as a

Images